> ## Documentation Index
> Fetch the complete documentation index at: https://agentic.proxify.io/llms.txt
> Use this file to discover all available pages before exploring further.

# The Maturity Ladder

> Four levels of working with AI — from vibe coding to production-grade engineering.

<Tip>**Flexibility is the skill** — The goal isn't to always operate at Level 4. It's to match the level to the stakes. A throwaway script doesn't need interactive code reviews. A payments refactor does.</Tip>

## The four levels

<Steps>
  <Step title="Vibe coding" icon="sparkles">
    Let AI go wild. No version control, no review, no guardrails. You accept whatever it produces and move on.

    **When it's appropriate:** Prototypes, throwaway scripts, learning experiments, anything you'll delete tomorrow.

    **When it's not:** Anything that ships to users, touches production data, or lives longer than a week.
  </Step>

  <Step title="Agentic coding with discipline" icon="shield-check">
    You're using AI to write code, but with basic engineering hygiene:

    * Git for version control — commit before and after delegating
    * File-level understanding of what changed and why
    * Basic security awareness (no secrets in code, no open permissions)
    * Sufficient test coverage to catch regressions

    This is where most engineers should start. It's fast and the safety floor is reasonable.
  </Step>

  <Step title="Agentic software engineering" icon="gears">
    The AI is doing more, but you've built guardrails around it:

    * **Pre-commit hooks** enforce formatting, linting, and secret scanning
    * **CI pipelines** catch what local checks miss
    * **Function-level understanding** — you know what every function does, even if you didn't write it
    * **Thorough testing** — unit, integration, edge cases
    * **One-shot AI code reviews** — ask Claude to review the diff before you merge
  </Step>

  <Step title="High-quality software engineering" icon="award">
    Maximum quality. You understand every line, and you use AI to deepen that understanding:

    * **Line-by-line understanding** of all changes
    * **Self-reflection loops** — "Are you sure about this approach? What about X?" Forces the model to catch its own mistakes before you have to
    * **Interactive AI code reviews** — back-and-forth dialogue about design decisions, not just a thumbs-up
    * **Advanced research** — use Claude to explore alternatives, read docs, compare approaches before committing to one
    * **AI-powered quality control** — background testing sessions, Playwright for web apps, automated regression checks
  </Step>
</Steps>

## At a glance

<CardGroup cols={2}>
  <Card title="Level 1: Vibe coding" icon="sparkles">
    **Quality:** Low · **Speed:** Lightning

    **Testing:** Bare minimum · **Reviews:** None
  </Card>

  <Card title="Level 2: Agentic coding with discipline" icon="shield-check">
    **Quality:** Okay · **Speed:** Faster

    **Testing:** Sufficient · **Reviews:** Brief
  </Card>

  <Card title="Level 3: Agentic software engineering" icon="gears">
    **Quality:** Medium · **Speed:** Fast

    **Testing:** Thorough · **Reviews:** One-shot
  </Card>

  <Card title="Level 4: High-quality SE" icon="award">
    **Quality:** High · **Speed:** Decent

    **Testing:** Rock solid · **Reviews:** Interactive
  </Card>
</CardGroup>

<Note>**More tokens ≠ more slop** — A common misconception: spending more tokens means more AI-generated slop. That's only true if the tokens go toward generating more code. When tokens go toward **research**, **self-reflection**, and **deeper understanding**, quality goes up — not down. Level 4 uses more tokens than Level 1. But the tokens buy verification, not volume.</Note>

***